Use AutoML to create high-quality models with just a few clicks
summary
Amazon SageMaker Autopilot takes a CSV or table, inspects features, trains hundreds of models with automated feature engineering and hyperparameter tuning, and recommends a winner deployable with one click or a single API call. It integrates with Redshift and Athena, writes artifacts to S3, and optimizes instance size during training. Autopilot produces outputs EDA and candidate notebooks showing transformations, algorithms tried (XGBoost, LinearLearner, etc.), and metrics — one user sees accuracy jump from 76% to 91%.
AI-written summary · about
chapters (14)
- 0:00Introduction
- 0:34Agenda
- 0:55Mission of AutoML
- 2:11What is tabular data
- 3:04Use cases
- 4:09Machine learning life cycle
- 10:26AutoML core features
- 15:00Amazon SageMaker Studio
- 15:36Create an AutoML experiment
- 20:26Notebooks
- 27:46Freddys
- 29:08Candy
- 29:58Resources
- 30:31Outro
related talks
31mUse AutoML to create high-quality models with just a few clicks
32mBuild quality ML models easily & quickly with Amazon SageMaker Autopilot
30mBring AutoML to all users across your business
31mPut Your Machine Learning on Autopilot
29mAutomatically Build Models With Amazon Sagemaker
31mTrain and tune ML models to the highest accuracy using Amazon SageMaker
41mUse AutoML to Create High-Quality Models
52mGenerate ML predictions without writing any code